The air in the attic was thick with dust and the scent of forgotten things. Mark found the list nestled within a box of old photographs, a small, worn notebook he recognized as belonging to his wife, Carol. He felt as if gravity had increased tenfold.

“Travel the Silk Road.” “Learn to paint.” “Run a marathon.” Each entry seemed to echo with the dreams they had shared, and those she had, perhaps, kept private. He was leaning against a dusty trunk, his legs feeling weak.

He felt a profound exhaustion, an overwhelming desire to simply cease existing in this moment. The shadows in the attic seemed to deepen, and he felt his knees buckle. He lowered himself to the floor, resting his back against the cool wood.

Emotion: sleepy

Cluster: Fatigue / Lethargy
PC1 (Valence): -0.86 Negative
PC2 (Disposition): -1.55

Role in Research

This story is one of 1,000 stories generated for the emotion sleepy. During extraction, it was fed through Gemma4-31B and its hidden state activations were captured at 11 layers.

The mean activation across all 1,000 sleepy stories, after denoising with neutral dialogue baselines, produces the sleepy emotion vector -- a direction in the model's 5,376-dimensional representation space.

Logit Lens (Layer 40)

Tokens promoted/suppressed when the sleepy vector is projected through the unembedding matrix.

Promoted:
😴0.318
weary0.310
fatigue0.296
💤0.283
似乎0.280
Suppressed:
B-0.343
C-0.294
because-0.293
భి-0.281
เพราะ-0.277